19
Jul
[Submitted on 17 Jul 2024] View a PDF of the paper titled GeoGuide: Geometric guidance of diffusion models, by Mateusz Poleski and 2 other authors View PDF HTML (experimental) Abstract:Diffusion models are among the most effective methods for image generation. This is in particular because, unlike GANs, they can be easily conditioned during training to produce elements with desired class or properties. However, guiding a pre-trained diffusion model to generate elements from previously unlabeled data is significantly more challenging. One of the possible solutions was given by the ADM-G guiding approach. Although ADM-G successfully generates elements from the given class,…